Transmission power control of wireless sensor networks based on optimal connectivity

Abstract To develop a short-term traffic load prediction model for satellite networks, a prediction algorithm based on spatiotemporal correlation and least square support vector machine (STLS-SVM) is presented. The prediction model fully exploits the regularity and periodicity of satellite constellations and uses the lag correlation coefficients to determine which satellite pairs have the highest spatiotemporal correlation. Then, the traffic time sequences of the most highly correlated satellites are taken as input feature vectors for training the LS-SVM for short-term traffic prediction. A simulation test shows that the algorithm has higher network flow prediction accuracy and that using the spatiotemporal correlation improves the predictive performance.